A system and methodology combines virtual reality (VR) with a plurality of machine learning analyses, and uses majority voting to detect dementia and the diseases under dementia. The accuracy of the classification in the Medical Visuospatial Dementia test is very high.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A visuospatial disorders detection method, comprising: presenting to a subject a three dimensional (3D) virtual reality environment in which the subject utilizes a multidirectional input device to input answers to questions and to guide an avatar on a path through the 3D virtual reality environment, wherein said multidirectional input device at least moves front, back, left and right; receiving input data for the subject generated by the subject's use of the multidirectional input device which comprises answers to questions input by the subject, coordinates and direction of the avatar relative to the path through the 3D virtual reality environment, and a time period used by the subject to guide the avatar along the path through the 3D virtual reality environment; supplying the received input data into a plurality of machine learning algorithms which utilizes correct and incorrect answers input by the subject, number of changes in direction of the avatar as the subject moves the avatar relative to the path through the 3D virtual reality environment, and the time period used by the subject to guide the avatar along the path through the 3D virtual reality environment, wherein the plurality of machine learning algorithms comprise Decision Tree Classifier, Extra Tree Classifier, AdaBoost Classifier, XGB Classifier, Gradient Boosting Classifier, Support Vector Classifier, Random Forest Classifier, Multinomial Naive Bayes, K-Neighbors Classifier, and Multilayer Perceptron; using machine learning with each of the plurality of machine learning algorithms to classify the subject into one of three classification labels selected from the group consisting of normal, demented, and mild cognitive impairment; and feeding results obtained with each of the plurality of machine learning algorithms into a system of voting to produce a final classification, wherein the system of voting comprises hard voting which predicts the final classification based on a most frequently used classification label produced by the machine learning using the plurality of machine learning algorithms.
The method detects visuospatial disorders by evaluating a subject's performance in a 3D virtual reality (VR) environment. The subject interacts with the environment using a multidirectional input device, such as a joystick or similar controller, to navigate an avatar along a predefined path while answering questions. The input device allows movement in four directions: front, back, left, and right. The system collects input data, including the subject's answers (correct or incorrect), the avatar's coordinates and direction relative to the path, and the time taken to complete the task. This data is analyzed using multiple machine learning algorithms, including Decision Tree Classifier, Extra Tree Classifier, AdaBoost Classifier, XGB Classifier, Gradient Boosting Classifier, Support Vector Classifier, Random Forest Classifier, Multinomial Naive Bayes, K-Neighbors Classifier, and Multilayer Perceptron. Each algorithm classifies the subject into one of three categories: normal, demented, or mild cognitive impairment. The results from all algorithms are then combined using hard voting, where the most frequently predicted classification label is selected as the final result. This approach aims to improve the accuracy of visuospatial disorder detection by leveraging multiple machine learning models and aggregating their predictions.
2. The method of claim 1 wherein the input data received from the subject answering questions and guiding the avatar relative to the path through the 3D virtual reality environment represent testing of both memory and visuospatial function.
This invention relates to a method for assessing cognitive functions, specifically memory and visuospatial abilities, using a 3D virtual reality (VR) environment. The method involves presenting a subject with a virtual reality environment containing a path and an avatar. The subject interacts with the environment by answering questions and guiding the avatar along the path. The input data generated from these interactions is used to evaluate both memory and visuospatial functions. The method may include displaying the avatar in a first-person or third-person perspective, allowing the subject to navigate the environment while performing tasks that require recalling information and spatial reasoning. The system may also track the subject's performance metrics, such as accuracy, response time, and navigation efficiency, to assess cognitive function. The method is designed to provide an immersive and interactive way to test cognitive abilities, potentially useful in clinical or research settings for diagnosing or monitoring neurological conditions.
3. The method of claim 1 wherein the input data received from the subject answering questions and guiding the avatar relative to the path through the 3D virtual reality environment represent testing of each of navigation, visual memory, and memory function.
This invention relates to a method for assessing cognitive functions, particularly navigation, visual memory, and memory function, using a 3D virtual reality (VR) environment. The method involves presenting a subject with a virtual environment where they interact with an avatar to navigate a predefined path. The subject answers questions and guides the avatar through the environment, with their inputs serving as data for cognitive testing. The virtual environment is designed to evaluate navigation skills by requiring the subject to traverse specific routes, visual memory by presenting and recalling visual cues, and general memory function through tasks that assess recall and recognition. The system tracks the subject's performance, including accuracy, response time, and path efficiency, to generate a cognitive assessment. The method may include adaptive difficulty adjustments based on the subject's performance to ensure accurate and comprehensive testing. The VR environment provides an immersive and controlled setting for standardized cognitive evaluation, reducing variability compared to traditional testing methods. The system may also include feedback mechanisms to guide the subject and ensure proper interaction with the avatar. The overall approach aims to provide a reliable, engaging, and scalable tool for cognitive assessment in clinical, research, or educational settings.
4. A visuospatial disorders detection method, comprising: presenting to a subject a three dimensional (3D) virtual reality environment in which the subject utilizes a multidirectional input device to input answers to questions and to guide an avatar on a path through the 3D virtual reality environment; receiving input data for the subject generated by the subject's use of the multidirectional input device which comprises answers to questions input by the subject, coordinates and direction of the avatar relative to the path through the 3D virtual reality environment, and a time period used by the subject to guide the avatar along the path through the 3D virtual reality environment; supplying the received input data into a plurality of machine learning algorithms which utilizes correct and incorrect answers input by the subject, number of changes in direction of the avatar as the subject moves the avatar relative to the path through the 3D virtual reality environment, and the time period used by the subject to guide the avatar along the path through the 3D virtual reality environment, wherein the plurality of machine learning algorithms comprise Decision Tree Classifier, Extra Tree Classifier, AdaBoost Classifier, XGB Classifier, Gradient Boosting Classifier, Support Vector Classifier, Random Forest Classifier, Multinomial Naive Bayes, K-Neighbors Classifier, and Multilayer Perceptron; using machine learning with each of the plurality of machine learning algorithms to classify the subject into one of three classification labels selected from the group consisting of normal, demented, and mild cognitive impairment; and feeding results obtained with each of the plurality of machine learning algorithms into a system of voting to produce a final classification, wherein the system of voting comprises soft voting which predicts the final classification based on averaging classification labels produced by the machine learning using the plurality of machine learning algorithms.
This invention relates to a method for detecting visuospatial disorders, such as dementia or mild cognitive impairment, using a 3D virtual reality (VR) environment. The method involves presenting a subject with a 3D VR environment where they interact using a multidirectional input device to answer questions and navigate an avatar along a predefined path. The system records input data, including the subject's answers, the avatar's coordinates and direction relative to the path, and the time taken to complete the task. This data is analyzed using multiple machine learning algorithms, including Decision Tree Classifier, Extra Tree Classifier, AdaBoost Classifier, XGB Classifier, Gradient Boosting Classifier, Support Vector Classifier, Random Forest Classifier, Multinomial Naive Bayes, K-Neighbors Classifier, and Multilayer Perceptron. Each algorithm evaluates the subject's performance based on correct/incorrect answers, directional changes, and task completion time. The results from all algorithms are combined using soft voting, where the final classification (normal, demented, or mild cognitive impairment) is determined by averaging the predictions. This approach leverages multiple machine learning models to improve diagnostic accuracy for visuospatial disorders.
5. The method of claim 4 wherein the input data received from the subject answering questions and guiding the avatar relative to the path through the 3D virtual reality environment represent testing of both memory and visuospatial function.
This invention relates to a method for assessing cognitive functions, specifically memory and visuospatial abilities, using a 3D virtual reality (VR) environment. The method involves presenting a subject with a virtual reality environment containing a path and an avatar. The subject interacts with the environment by answering questions and guiding the avatar along the path. The input data generated from these interactions is used to evaluate both memory and visuospatial function. The VR environment may include obstacles, landmarks, or other elements that require the subject to navigate and recall information, thereby testing their cognitive abilities. The method may also involve tracking the subject's performance metrics, such as accuracy, response time, and navigation efficiency, to provide a comprehensive assessment of their cognitive state. This approach leverages immersive VR technology to create a dynamic and engaging testing environment that can be adapted for various diagnostic or therapeutic applications.
6. The method of claim 4 wherein the input data received from the subject answering questions and guiding the avatar relative to the path through the 3D virtual reality environment represent testing of each of navigation, visual memory, and memory function.
This invention relates to a method for assessing cognitive functions, specifically navigation, visual memory, and memory function, using a 3D virtual reality (VR) environment. The method involves a subject interacting with an avatar within the VR environment, where the subject answers questions and guides the avatar along a predefined path. The input data generated from these interactions is used to evaluate the subject's cognitive abilities. The VR environment is designed to simulate real-world scenarios, allowing the subject to navigate through the space while performing tasks that test different cognitive functions. For navigation, the subject must guide the avatar through the environment, demonstrating spatial awareness and pathfinding skills. Visual memory is assessed by presenting the subject with visual stimuli within the VR environment and requiring them to recall or recognize these elements later. Memory function is evaluated by testing the subject's ability to retain and retrieve information over time, such as remembering specific locations, objects, or sequences of events within the VR environment. The method provides a structured way to measure cognitive performance in a controlled, immersive setting, offering insights into the subject's cognitive strengths and weaknesses. This approach can be used for diagnostic purposes, rehabilitation, or research in fields such as neuroscience, psychology, and cognitive assessment. The use of VR enhances the realism and engagement of the assessment, potentially improving the accuracy and reliability of the results compared to traditional testing methods.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
November 4, 2020
February 15, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.